Abstract
Artificial intelligence (AI) has transformed modern drug discovery by reshaping how therapeutic targets are identified, validated, and optimized. Coumarin derivatives, with their diverse pharmacological activities and structural adaptability, offer a rich chemical space for AI-guided exploration. However, despite the potential of integrating AI methodologies with coumarin chemistry to accelerate the identification of novel disease targets and design safer, more efficient drug candidates, a unified synthesis of these data-driven workflows remains lacking. This review aims to address this research gap by compiling and analyzing literature from the past ten years to provide a comprehensive content framework. The objective is to evaluate data-driven approaches-ranging from literature-based data mining, molecular docking, and predictive modeling to deep-learning frameworks and multiomics integration-that collectively enhance coumarin-target discovery. Emphasis is placed on AI-enabled workflows that connect structural, functional, and phenotypic data to support hypothesis generation, target prioritization, and validation across computational and experimental domains. Recent studies demonstrate that AI-assisted algorithms can accurately predict coumarin-protein interactions, uncover unrecognized biological targets, and rationalize structure-activity relationships. Deep-learning and risk-benefit models have improved target ranking, while multiomics data fusion has revealed disease-specific mechanisms in oncology, metabolic, infectious, and cardiovascular disorders. These insights have translated into tangible outcomes, such as the design of novel coumarin-quinone hybrids and selective enzyme inhibitors. The convergence of AI and coumarin-based medicinal chemistry heralds a paradigm shift in therapeutic target identification. Future research directions and prospects should focus on ethical data governance, interpretability, and cross-disciplinary collaboration to position AI-driven coumarin research at the forefront of next-generation precision therapeutics.